Add VC Noro model

[kenxxxxx]

✨ Description

In this PR, we release an unofficial PyTorch implementation of Noro, a Noise-Robust One-shot Voice Conversion (VC) system. This model is designed to convert the timbre of speech from a source speaker to a target speaker using only a single reference speech sample while preserving the semantic content of the original speech. Noro introduces innovative components tailored for VC using noisy reference speeches, including a dual-branch reference encoding module and a noise-agnostic contrastive speaker loss.

The main purpose of this PR is to provide a noise-robust VC solution that performs effectively even with noisy reference speeches, making it suitable for real-world applications. Additionally, we explore the hidden speaker representation capabilities of the VC system by repurposing its reference encoder as a speaker encoder, demonstrating competitive performance with advanced self-supervised learning models.

To test this PR, follow the instructions in the updated README.md to set up the environment, train the model, and evaluate its performance under different acoustic environments.

🚧 Related Issues

None

👨‍💻 Changes Proposed

• Implemented the Noro model with a dual-branch reference encoding module.
• Added the training and evaluation scripts for the Noro model.
• Added detailed documentation and examples for training and testing the model.

🧑‍🤝‍🧑 Who Can Review?

@RMSnow @HarryHe11 @Adorable-Qin

✅ Checklist

• Code has been reviewed
• Code complies with the project's code standards and best practices
• Code has passed all tests
• Code does not affect the normal use of existing features
• Code has been commented properly
• Documentation has been updated (if applicable)
• Demo/checkpoint has been attached (if applicable)

[RMSnow]

Thanks for your efforts! Great job! This is our first time to introduce VC. So let us set high criteria for future developers!

[HarryHe11]

@RMSnow Thank you, Xueyao, for your detailed comments! @kenxxxxx Yuchen, please familiarize yourself with Git-based development and directly update your code on your fork so we can track your revision progress.

[RMSnow]

Voice Conversion Recipe

[RMSnow]

Typo: "SVC model"

[RMSnow]

Will this change effect the ns2, TTS model?

[RMSnow]

BTW, use black to format the code to pass the format check